WorldScape-Policy-2

WorldScape-Policy-2: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory

WorldScape Policy 2.0 is a controllable World Action Model (WAM) with reasoning-augmented long short-term memory for long-horizon robotic manipulation, fine-grained instruction following, visual-context reasoning, and in-context skill transfer.

• Model is coming soon. We are preparing the pre-training model and post-training checkpoint of RoboTwin 2.0 dataset for release.
• Project page: https://manifoldai-research.github.io/WorldScape-Policy/

Citation

@article{worldscape-policy-2,
  title={WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory},
  author={Haisheng Su and Zongdai Liu and Xin Jin and Haoxuan Dou and Chengming Hu and Baorun Li and Zhanwang Liu and Ruiyan Xu and Jianjie Fang and Xin Zhang and Zhenjie Yang and Xue Yang and Chen Gao and Junchi Yan and Yong Li and Wei Wu},
  journal={arXiv preprint arXiv:2607.18840},
  year={2026}
}